{"id":"2609.02359","title":"TempoGround: State-Aware Streaming Visual Grounding with Vision-Language Models","url":"https://codeofpaper.com/paper/2609.02359","arxiv_url":"https://arxiv.org/abs/2609.02359","published":"2026-09-02","code":"none","best":null,"most_starred_community":null,"implementations":[],"possible_matches":2}